zap
044e36f385
fix(n8n-webhook): auto-load local gog automation env
2026-03-12 19:16:24 +00:00
zap
afa48a3aa6
feat(n8n-webhook): bridge approvals to gog executors
2026-03-12 18:29:33 +00:00
zap
1eabaeb652
feat(n8n-webhook): add approval-gated notification executor
2026-03-12 17:41:59 +00:00
zap
dc990a1af3
fix(n8n-webhook): deploy and verify expanded action bus
2026-03-12 17:33:26 +00:00
zap
9dcc477a98
feat(n8n-webhook): expand action bus starter workflow
2026-03-12 17:22:58 +00:00
zap
aa0914f734
feat(n8n): add get-logs action
2026-03-12 16:45:19 +00:00
zap
c1f851b451
feat(n8n): wire notify and persist append logs
2026-03-12 15:03:35 +00:00
zap
9b8b744cb1
fix(skill): simplify n8n action router
2026-03-12 07:32:40 +00:00
zap
e0a3694430
feat(skill): finish n8n webhook skill
2026-03-12 07:07:21 +00:00
zap
295809b161
feat(skill): add n8n action-bus helper
2026-03-12 06:51:15 +00:00
zap
7a44225481
feat(skill): add local n8n webhook skill draft
2026-03-12 06:47:00 +00:00
zap
680daf9964
feat(council): define litellm-backed tier policy
2026-03-11 20:46:48 +00:00
zap
e353be8814
feat(council): add executable roster and tier planner
2026-03-11 20:32:52 +00:00
zap
9e9f7996e9
docs(council): target dedicated council agents by role
2026-03-11 20:26:29 +00:00
zap
eb9522d5c2
feat(skills): install gog-calendar
2026-03-10 21:25:44 +00:00
zap
8d288918e3
docs(search): record routing policy and fallback tuning
2026-03-10 20:04:32 +00:00
zap
1de793fb8d
feat(search): add local meta search wrapper
2026-03-10 19:55:44 +00:00
zap
610f2e40b8
fix(search): stabilize brave mcp skill args
2026-03-10 19:53:37 +00:00
zap
d98174b609
feat(search): add local brave mcp search skill
2026-03-10 19:46:26 +00:00
zap
54b4435aaa
feat(skills): add inbox-priority-agent triage skill
2026-03-09 19:00:40 +00:00
zap
21f8c374e8
feat(skills): add clawddocs skill v1.2.2
2026-03-06 00:40:01 +00:00
zap
ad385d6462
chore(model-hints): sync OpenAI and Anthropic best-practice guidance
2026-03-05 21:29:09 +00:00
zap
52c64e6f39
feat(skills): add model-family hint files for agent:bootstrap injection (anthropic/openai/generic)
2026-03-05 20:55:23 +00:00
zap
06202bcfbe
chore(skills): drop OpenAI o-series from llm-tool-best-practices scope
2026-03-05 20:44:57 +00:00
zap
a34826908d
feat(skills): add llm-tool-best-practices reference from Anthropic + OpenAI official docs
2026-03-05 20:44:00 +00:00
zap
e08e3d65e9
feat(council): add D/P (Deterministic/Probabilistic) dual-group mode
...
- New 'mode' parameter: personality (default) or dp
- D group: grounded, feasibility-first (Freethinker + Arbiter)
- P group: exploratory, reframing-first (Freethinker + Arbiter)
- Meta-Arbiter merges best ideas from both groups
- Full prompt templates for ideation, assessment, bridge, and merge
- Orchestration docs for single-round and multi-round D/P flows
- Inspired by Flynn's dual-council architecture, adapted for OpenClaw subagents
2026-03-05 19:18:44 +00:00
zap
3e198bcbb3
docs(council): add experimental findings from all 3 flow types
...
- Tested parallel 1-round, sequential 1-round, debate/parallel 3-round
- 3 rounds is sweet spot: positions converge, meaningful evolution
- Sequential most token-efficient; parallel 3-round best depth-to-cost
- Debate and parallel 3-round mechanically identical (prompt tone differs)
- Added cost profiles, recommended defaults by use case
- Updated TODOs: unify flows, test 2-round, test mixed model tiers
2026-03-05 16:39:32 +00:00
zap
da36000050
feat(council): add configurable rounds, flow parameters, and round-specific prompts
...
- Parameters: flow (parallel/sequential/debate), rounds (1-5), tier (light/medium/heavy)
- Round-specific prompt templates: opening, rebuttal, final position
- Multi-round referee template tracks position evolution across rounds
- Word count guidance decreases per round to control token cost
- Subagent labeling convention: council-r{round}-{role}
- Updated from live testing with 1-round and 3-round parallel debates
2026-03-05 16:21:22 +00:00
zap
7274d399ce
feat(council): add council advisory skill with parallel/sequential/debate flows
...
- 3 advisors (Pragmatist, Visionary, Skeptic) + 1 Referee subagent
- Default: parallel + synthesis flow
- Prompt templates in references/prompts.md
- Model tier selection based on topic complexity
- Added TODO tasks for personality depth and skill name revisit
2026-03-05 08:41:35 +00:00
zap
808af5ee13
chore(workspace): add hardened startup/security workflows and skill suite
2026-03-04 19:13:33 +00:00
